各位大虾，我在网上看到的教程里的一个程序段，本来想要试试看的： [I '0,y
net=newff([-1 2; 0 5],[3,1],{'tansig','purelin'},'traingd'); Tl(^
net.trainParam.show = 50; D!{Y$;
net.trainParam.lr = 0.05; t3*wjQ3
net.trainParam.epochs = 300; ZZ2vvtlyG
net.trainParam.goal = 1e-5; ML w7 }[
p = [-1 -1 2 2;0 5 0 5]; `eE& 5.
t = [-1 -1 1 1]; @mOH"acGn?
net=train(net,p,t); G_;)a]v8)
TRAINGD, Epoch 0/300, MSE 1.59423/1e-05, Gradient 2.76799/1e-10 HePUWL'
TRAINGD, Epoch 50/300, MSE 0.00236382/1e-05, Gradient 0.0495292/1e-10 iHeN9 cl
TRAINGD, Epoch 100/300, MSE 0.000435947/1e-05, Gradient 0.0161202/1e-10 d"}k!
0m
TRAINGD, Epoch 150/300, MSE 8.68462e-05/1e-05, Gradient 0.00769588/1e-10 K &POyOvT
TRAINGD, Epoch 200/300, MSE 1.45042e-05/1e-05, Gradient 0.00325667/1e-10 .a O,8M
TRAINGD, Epoch 211/300, MSE 9.64816e-06/1e-05, Gradient 0.00266775/1e-10 Rp .Sj{<2
TRAINGD, Performance goal met. mg^I=kpk
a = sim(net,p) UtPLI al
plot(p,t,p,a,'o') \Jx04[=
但是为什么老是报错： aC$B2
??? Input argument "net" is undefined. m? eiIrMW
